© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13517
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams or sporting events

    oai_token-act-pair · gemini-2.0-flash

    Mixed news/sports/science texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ref
    -0.48
    charis
    -0.46
    requestCode
    -0.44
     Descartes
    -0.42
     kios
    -0.41
     سبيل
    -0.41
    cti
    -0.40
     незавершена
    -0.40
    phar
    -0.40
     podat
    -0.40
    POSITIVE LOGITS
    Datuak
    0.80
     Big
    0.78
     يتيمه
    0.73
     dàng
    0.71
    WriteLiteral
    0.70
    migrationBuilder
    0.68
    MLLoader
    0.68
    IndentedString
    0.65
     <=",
    0.65
    aarrggbb
    0.64
    Activations Density 1.774%

    No Known Activations